Mapping wetland using the object-based stacked generalization method based on multi-temporal optical and SAR data

Yaotong Cai, Xinyu Li, Meng Zhang, Hui Lin
2020 International Journal of Applied Earth Observation and Geoinformation  
A B S T R A C T Wetland ecosystems have experienced dramatic challenges in the past few decades due to natural and human factors. Wetland maps are essential for the conservation and management of terrestrial ecosystems. This study is to obtain an accurate wetland map using an object-based stacked generalization (Stacking) method on the basis of multi-temporal Sentinel-1 and Sentinel-2 data. Firstly, the Robust Adaptive Spatial Temporal Fusion Model (RASTFM) is used to get time series Sentinel-2
more » ... NDVI, from which the vegetation phenology variables are derived by the threshold method. Subsequently, both vertical transmit-vertical receive (VV) and vertical transmit-horizontal receive (VH) polarization backscatters (σ0 VV, σ0 VH) are obtained using the time series Sentinel-1 images. Speckle noise inherent in SAR data, resulting in over-segmentation or under-segmentation, can affect image segmentation and degrade the accuracies of wetland classification. Therefore, we segment Sentinel-2 multispectral images to delineate meaningful objects in this study. Then, in order to reduce data redundancy and computation time, we analyze the optimal feature combination using the Sentinel-2 multispectral images, Sentinel-2 NDVI time series, phenological variables and other vegetation index derived from Sentinel-2 multispectral images, as well as time series Sentinel-1 backscatters at the object level. Finally, the stacked generalization algorithm is utilized to extract the wetland information based on the optimal feature combination in the Dongting Lake wetland. The overall accuracy and Kappa coefficient of the object-based stacked generalization method are 92.46% and 0.92, which are 3.88% and 0.04 higher than that using the pixel-based method. Moreover, the object-based stacked generalization algorithm is superior to single classifiers in classifying vegetation of high heterogeneity areas. between the vegetation types when mono-temporal multispectral images are used. Time series optical satellite images are able to periodically capture the phenological information of wetland vegetation and can generate wetland maps with high accuracy . Additionally, images of spring and autumn are able to optimize the separability between vegetation types (Deventer et al., 2019) . MODIS, Landsat and SPOT images have been widely and successfully used for monitoring the wetland vegetation and detecting the presence and extent of flood (Evans and Costa, 2013; Hou et al., 2018; Zhou et al., 2016) . However, their spectral and spatial resolutions may compromise detail wetland vegetation type identification. Moreover, traditional multispectral sensors, such as the Landsat TM/ETM+/OLI, often have saturation of reflected signals in the red and near-infrared (NIR)
doi:10.1016/j.jag.2020.102164 fatcat:ztjhrv4uyrbw3cdkyjb7co6e6u